A Topic Study of Microblog Based on Specific Events

Abstract:

This paper describes the study of topics on microblog based on specific events. First, we use a famous topic model LDA to extract topics from microblog about events. Then, we propose three indexes: Attention Factor (AF), Evolution Factor (EF) to see the performance of microblog topics and Diversity Factor (DF) to calculate the divergence of topics from microblog and news reports. Finally, we choose corpuses for four events to study. The experiments show that, on specific events: 1) There are more critical topics, while factual topics less, and both of them get close AFs. 2) Critical topics last long on microblog and have lower EFs, which means their contents vary little, but factual topics last intermittently and their contents vary greatly. 3) To compare with the same events from news reports, critical topics use totally different words, but factual topics use close words.

• Periodical: Applied Mechanics and Materials (Volumes 347-350)
• Pages: 2625-2630
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.347-350.2625
• Online since: August 2013
• Authors: Zhen Yu Zhou, Fang Li
• Keywords: Microblog, Topic Model, Trend

References

[1] D.M. Blei, A.Y. Ng, and M.I. Jordan. Latent Dirichlet Allocation. The Journal of Machine Learning Research, 2003, vol. 3, pp.993-1022.

[2] D.M. Blei, J.D. Lafferty. A Correlated Topic Model of Science. The Annals of Applied Statistics 2007, Vol. 1, No. 1, pp.17-35.

[3] D.M. Blei and J.D. Lafferty. Dynamic Topic Model. In International conference on Machine Learning, 2006, pp.113-120.

[4] LiangjieHong, and B.D. Davison. Empirical study of topic modeling in Twitter. Proceedings of the SIGKDD Workshop on SMA, (2008).

[5] Xin Zhao, Jing Jiang, JianshuWeng, et al. Comparing Twitter and traditional media using topic models. In Proceedings of the European Conference on Information Retrieval, (2011).

[6] D. Ramage, S. Dumais, and D. Liebling. Characterizing Microblogs with Topic Models. Proceedings of AAAI on Weblogs and Social Media, (2010).

DOI: 10.1609/icwsm.v4i1.14026

[7] D. Ramage, D. Hall, R. Nallapati, et al. Labeled LDA: a supervised topic model for credit attribution in multi-labeled corpora. Proceedings of the Conference on Empirical Methods in Natural Language Processing, (2009).

DOI: 10.3115/1699510.1699543

[8] Yan Qu, Chen Huang, Pengyi Zhang, et al. Microblogging after a Major Disaster in China: A Case Study of the 2010 Yushu Earthquake. Proceedings of the ACM 2011 conference on Computer supported cooperative work, 2011, pp.25-34.

DOI: 10.1145/1958824.1958830

[9] S. Vieweg, A.L. Hughes, K. Starbird, et al. Microblogging During Two Natural Hazards Events: What Twitter May Contribute to Situational Awareness. Proceedings of the 28th International Conference on Human factors in computing systems, 2010, pp.1079-1088.

DOI: 10.1145/1753326.1753486

[10] S. Geman, D. Geman. Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1984, Vol. 6, No. 6, p.721–741.

DOI: 10.1109/tpami.1984.4767596